Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -element
    -0.07
    ></
    -0.07
     Lever
    -0.06
    mět
    -0.06
    _Comm
    -0.06
     advantageous
    -0.06
     DAG
    -0.06
    βε
    -0.06
    _DISTANCE
    -0.06
     Artists
    -0.06
    POSITIVE LOGITS
     anyway
    0.07
     저
    0.07
    串
    0.07
    (serializer
    0.06
     (__
    0.06
    官
    0.06
     UITableViewCell
    0.06
    ύτε
    0.06
     (%
    0.06
    Ball
    0.06
    Act Density 0.019%

    No Known Activations